[tip:x86/security] x86: Add NX protection for kernel data

From: tip-bot for Matthieu Castet
Date: Thu Nov 18 2010 - 09:09:42 EST


Commit-ID: 5bd5a452662bc37c54fb6828db1a3faf87e6511c
Gitweb: http://git.kernel.org/tip/5bd5a452662bc37c54fb6828db1a3faf87e6511c
Author: Matthieu Castet <castet.matthieu@xxxxxxx>
AuthorDate: Tue, 16 Nov 2010 22:31:26 +0100
Committer: Ingo Molnar <mingo@xxxxxxx>
CommitDate: Thu, 18 Nov 2010 12:52:04 +0100

x86: Add NX protection for kernel data

This patch expands functionality of CONFIG_DEBUG_RODATA to set main
(static) kernel data area as NX.

The following steps are taken to achieve this:

1. Linker script is adjusted so .text always starts and ends on a page bound
2. Linker script is adjusted so .rodata always start and end on a page boundary
3. NX is set for all pages from _etext through _end in mark_rodata_ro.
4. free_init_pages() sets released memory NX in arch/x86/mm/init.c
5. bios rom is set to x when pcibios is used.

The results of patch application may be observed in the diff of kernel page
table dumps:

pcibios:

-- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400
++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400
0x00000000-0xc0000000 3G pmd
---[ Kernel Mapping ]---
-0xc0000000-0xc0100000 1M RW GLB x pte
+0xc0000000-0xc00a0000 640K RW GLB NX pte
+0xc00a0000-0xc0100000 384K RW GLB x pte
-0xc0100000-0xc03d7000 2908K ro GLB x pte
+0xc0100000-0xc0318000 2144K ro GLB x pte
+0xc0318000-0xc03d7000 764K ro GLB NX pte
-0xc03d7000-0xc0600000 2212K RW GLB x pte
+0xc03d7000-0xc0600000 2212K RW GLB NX pte
0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd
0xf7a00000-0xf7bfe000 2040K RW GLB NX pte
0xf7bfe000-0xf7c00000 8K pte

No pcibios:

-- data_nx_pt_before.txt 2009-10-13 07:48:59.000000000 -0400
++ data_nx_pt_after.txt 2009-10-13 07:26:46.000000000 -0400
0x00000000-0xc0000000 3G pmd
---[ Kernel Mapping ]---
-0xc0000000-0xc0100000 1M RW GLB x pte
+0xc0000000-0xc0100000 1M RW GLB NX pte
-0xc0100000-0xc03d7000 2908K ro GLB x pte
+0xc0100000-0xc0318000 2144K ro GLB x pte
+0xc0318000-0xc03d7000 764K ro GLB NX pte
-0xc03d7000-0xc0600000 2212K RW GLB x pte
+0xc03d7000-0xc0600000 2212K RW GLB NX pte
0xc0600000-0xf7a00000 884M RW PSE GLB NX pmd
0xf7a00000-0xf7bfe000 2040K RW GLB NX pte
0xf7bfe000-0xf7c00000 8K pte

The patch has been originally developed for Linux 2.6.34-rc2 x86 by
Siarhei Liakh <sliakh.lkml@xxxxxxxxx> and Xuxian Jiang <jiang@xxxxxxxxxxx>.

-v1: initial patch for 2.6.30
-v2: patch for 2.6.31-rc7
-v3: moved all code into arch/x86, adjusted credits
-v4: fixed ifdef, removed credits from CREDITS
-v5: fixed an address calculation bug in mark_nxdata_nx()
-v6: added acked-by and PT dump diff to commit log
-v7: minor adjustments for -tip
-v8: rework with the merge of "Set first MB as RW+NX"

Signed-off-by: Siarhei Liakh <sliakh.lkml@xxxxxxxxx>
Signed-off-by: Xuxian Jiang <jiang@xxxxxxxxxxx>
Signed-off-by: Matthieu CASTET <castet.matthieu@xxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxx>
Cc: James Morris <jmorris@xxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxx>
Cc: Rusty Russell <rusty@xxxxxxxxxxxxxxx>
Cc: Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx>
Cc: Dave Jones <davej@xxxxxxxxxx>
Cc: Kees Cook <kees.cook@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
LKML-Reference: <4CE2F82E.60601@xxxxxxx>
[ minor cleanliness edits ]
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
arch/x86/include/asm/pci.h | 1 +
arch/x86/kernel/vmlinux.lds.S | 8 ++++++--
arch/x86/mm/init.c | 3 ++-
arch/x86/mm/init_32.c | 20 +++++++++++++++++++-
arch/x86/mm/init_64.c | 3 ++-
arch/x86/mm/pageattr.c | 5 ++++-
arch/x86/pci/pcbios.c | 23 +++++++++++++++++++++++
7 files changed, 57 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index ca0437c..6761292 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -65,6 +65,7 @@ extern unsigned long pci_mem_start;

#define PCIBIOS_MIN_CARDBUS_IO 0x4000

+extern int pcibios_enabled;
void pcibios_config_init(void);
struct pci_bus *pcibios_scan_root(int bus);

diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index e03530a..bf47007 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -69,7 +69,7 @@ jiffies_64 = jiffies;

PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
- data PT_LOAD FLAGS(7); /* RWE */
+ data PT_LOAD FLAGS(6); /* RW_ */
#ifdef CONFIG_X86_64
user PT_LOAD FLAGS(5); /* R_E */
#ifdef CONFIG_SMP
@@ -116,6 +116,10 @@ SECTIONS

EXCEPTION_TABLE(16) :text = 0x9090

+#if defined(CONFIG_DEBUG_RODATA)
+ /* .text should occupy whole number of pages */
+ . = ALIGN(PAGE_SIZE);
+#endif
X64_ALIGN_DEBUG_RODATA_BEGIN
RO_DATA(PAGE_SIZE)
X64_ALIGN_DEBUG_RODATA_END
@@ -335,7 +339,7 @@ SECTIONS
__bss_start = .;
*(.bss..page_aligned)
*(.bss)
- . = ALIGN(4);
+ . = ALIGN(PAGE_SIZE);
__bss_stop = .;
}

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index c0e28a1..947f42a 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -364,8 +364,9 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
/*
* We just marked the kernel text read only above, now that
* we are going to free part of that, we need to make that
- * writeable first.
+ * writeable and non-executable first.
*/
+ set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);

printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 0e969f9..f89b5bb 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -226,7 +226,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)

static inline int is_kernel_text(unsigned long addr)
{
- if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
+ if (addr >= (unsigned long)_text && addr <= (unsigned long)__init_end)
return 1;
return 0;
}
@@ -912,6 +912,23 @@ void set_kernel_text_ro(void)
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
}

+static void mark_nxdata_nx(void)
+{
+ /*
+ * When this called, init has already been executed and released,
+ * so everything past _etext sould be NX.
+ */
+ unsigned long start = PFN_ALIGN(_etext);
+ /*
+ * This comes from is_kernel_text upper limit. Also HPAGE where used:
+ */
+ unsigned long size = (((unsigned long)__init_end + HPAGE_SIZE) & HPAGE_MASK) - start;
+
+ if (__supported_pte_mask & _PAGE_NX)
+ printk(KERN_INFO "NX-protecting the kernel data: %luk\n", size >> 10);
+ set_pages_nx(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
void mark_rodata_ro(void)
{
unsigned long start = PFN_ALIGN(_text);
@@ -946,6 +963,7 @@ void mark_rodata_ro(void)
printk(KERN_INFO "Testing CPA: write protecting again\n");
set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
#endif
+ mark_nxdata_nx();
}
#endif

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 71a5929..ce59c05 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -788,6 +788,7 @@ void mark_rodata_ro(void)
unsigned long rodata_start =
((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
unsigned long end = (unsigned long) &__end_rodata_hpage_align;
+ unsigned long kernel_end = (((unsigned long)&__init_end + HPAGE_SIZE) & HPAGE_MASK);
unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table);
unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata);
unsigned long data_start = (unsigned long) &_sdata;
@@ -802,7 +803,7 @@ void mark_rodata_ro(void)
* The rodata section (but not the kernel text!) should also be
* not-executable.
*/
- set_memory_nx(rodata_start, (end - rodata_start) >> PAGE_SHIFT);
+ set_memory_nx(rodata_start, (kernel_end - rodata_start) >> PAGE_SHIFT);

rodata_test();

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 6f2a6b6..8b830ca 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -13,6 +13,7 @@
#include <linux/pfn.h>
#include <linux/percpu.h>
#include <linux/gfp.h>
+#include <linux/pci.h>

#include <asm/e820.h>
#include <asm/processor.h>
@@ -261,8 +262,10 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
* The BIOS area between 640k and 1Mb needs to be executable for
* PCI BIOS based config access (CONFIG_PCI_GOBIOS) support.
*/
- if (within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
+#ifdef CONFIG_PCI_BIOS
+ if (pcibios_enabled && within(pfn, BIOS_BEGIN >> PAGE_SHIFT, BIOS_END >> PAGE_SHIFT))
pgprot_val(forbidden) |= _PAGE_NX;
+#endif

/*
* The kernel text needs to be executable for obvious reasons
diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c
index 2492d16..a5f7d0d 100644
--- a/arch/x86/pci/pcbios.c
+++ b/arch/x86/pci/pcbios.c
@@ -9,6 +9,7 @@
#include <linux/uaccess.h>
#include <asm/pci_x86.h>
#include <asm/pci-functions.h>
+#include <asm/cacheflush.h>

/* BIOS32 signature: "_32_" */
#define BIOS32_SIGNATURE (('_' << 0) + ('3' << 8) + ('2' << 16) + ('_' << 24))
@@ -25,6 +26,27 @@
#define PCIBIOS_HW_TYPE1_SPEC 0x10
#define PCIBIOS_HW_TYPE2_SPEC 0x20

+int pcibios_enabled;
+
+/* According to the BIOS specification at:
+ * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could
+ * restrict the x zone to some pages and make it ro. But this may be
+ * broken on some bios, complex to handle with static_protections.
+ * We could make the 0xe0000-0x100000 range rox, but this can break
+ * some ISA mapping.
+ *
+ * So we let's an rw and x hole when pcibios is used. This shouldn't
+ * happen for modern system with mmconfig, and if you don't want it
+ * you could disable pcibios...
+ */
+static inline void set_bios_x(void)
+{
+ pcibios_enabled = 1;
+ set_memory_x(PAGE_OFFSET + BIOS_BEGIN, (BIOS_END - BIOS_BEGIN) >> PAGE_SHIFT);
+ if (__supported_pte_mask & _PAGE_NX)
+ printk(KERN_INFO "PCI : PCI BIOS aera is rw and x. Use pci=nobios if you want it NX.\n");
+}
+
/*
* This is the standard structure used to identify the entry point
* to the BIOS32 Service Directory, as documented in
@@ -332,6 +354,7 @@ static struct pci_raw_ops * __devinit pci_find_bios(void)
DBG("PCI: BIOS32 Service Directory entry at 0x%lx\n",
bios32_entry);
bios32_indirect.address = bios32_entry + PAGE_OFFSET;
+ set_bios_x();
if (check_pcibios())
return &pci_bios_access;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/